Hugging Face's logo

ntsema
/
wav2vec2-xlsr-53-espeak-cv-ft-evn4-ntsema-colab

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ntsema commited on
Commit
19ed735
•
1 Parent(s): 9ad7d8e

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +4 -0
  2. special_tokens_map.json +22 -0
  3. tokenizer_config.json +12 -0
  4. vocab.json +69 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 68,
3
+ "<s>": 67
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<s>",
19
+ "eos_token": "</s>",
20
+ "pad_token": "[PAD]",
21
+ "unk_token": "[UNK]"
22
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "./",
6
+ "pad_token": "[PAD]",
7
+ "replace_word_delimiter_char": " ",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
vocab.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 66,
3
+ "[UNK]": 65,
4
+ "a": 1,
5
+ "aː": 41,
6
+ "ā": 49,
7
+ "ā̄": 55,
8
+ "b": 2,
9
+ "bʲ": 61,
10
+ "c": 3,
11
+ "d": 4,
12
+ "dʲ": 50,
13
+ "e": 5,
14
+ "eː": 43,
15
+ "ē": 54,
16
+ "f": 6,
17
+ "g": 7,
18
+ "gʲ": 63,
19
+ "h": 8,
20
+ "i": 9,
21
+ "iː": 39,
22
+ "ī": 51,
23
+ "j": 10,
24
+ "k": 11,
25
+ "kʲ": 60,
26
+ "l": 12,
27
+ "lʲ": 36,
28
+ "m": 13,
29
+ "mʲ": 47,
30
+ "n": 14,
31
+ "nʲ": 37,
32
+ "ń": 44,
33
+ "o": 15,
34
+ "oː": 42,
35
+ "ō": 52,
36
+ "p": 16,
37
+ "pʲ": 59,
38
+ "r": 17,
39
+ "rʲ": 57,
40
+ "s": 18,
41
+ "sʲ": 38,
42
+ "t": 19,
43
+ "tʲ": 45,
44
+ "t͡ʃ": 46,
45
+ "u": 20,
46
+ "uː": 40,
47
+ "ū": 53,
48
+ "v": 21,
49
+ "vʲ": 58,
50
+ "w": 22,
51
+ "x": 23,
52
+ "y": 24,
53
+ "z": 25,
54
+ "zʲ": 62,
55
+ "|": 0,
56
+ "ø": 26,
57
+ "ŋ": 27,
58
+ "ɒ": 28,
59
+ "ɔ": 29,
60
+ "ə": 30,
61
+ "ə̄": 48,
62
+ "ɣ": 31,
63
+ "ɨ": 32,
64
+ "ɲ": 33,
65
+ "ʃ": 34,
66
+ "ʃʲ": 56,
67
+ "ʒ": 35,
68
+ "χ": 64
69
+ }